Scheduling tertiary I/O in database applications

We study the problem of scheduling I/O requests for tertiary storage libraries to improve performance. The focus is on scheduling policies that process all requests on a loaded medium before unloading it. For single drive settings, an efficient algorithm that produces optimal schedules is developed. For multiple drives, the problem is shown to be NP complete. Efficient and effective heuristics are presented for the multiple drives case. The scheduling policies developed achieve significant performance gains over more naive first come first served policies. The study is general enough to be applicable to any storage library handling removable media, such as tapes or optical disks.